Re: glusterfs under high load failing?

[Pranith Kumar Karampuri <pkarampu@xxxxxxxxxx>]

On 10/13/2014 10:03 PM, Roman wrote:

hmm,

seems like another strange issue? Seen this before. Had to restart the volume to get my empty space back.

root@glstor-cli:/srv/nfs/HA-WIN-TT-1T# ls -l

total 943718400

-rw-r--r-- 1 root root 966367641600 Oct 13 16:55 disk

root@glstor-cli:/srv/nfs/HA-WIN-TT-1T# rm disk

root@glstor-cli:/srv/nfs/HA-WIN-TT-1T# df -h

Filesystem                                              Size  Used Avail Use% Mounted on

rootfs                                                  282G  1.1G  266G   1% /

udev                                                     10M     0   10M   0% /dev

tmpfs                                                   1.4G  228K  1.4G   1% /run

/dev/disk/by-uuid/c62ee3c0-c0e5-44af-b0cd-7cb3fbcc0fba  282G  1.1G  266G   1% /

tmpfs                                                   5.0M     0  5.0M   0% /run/lock

tmpfs                                                   5.2G     0  5.2G   0% /run/shm

stor1:HA-WIN-TT-1T                                     1008G  901G   57G  95% /srv/nfs/HA-WIN-TT-1T

no file, but size is still 901G.

Both servers show the same.

Do I really have to restart the volume to fix that?

IMO this can happen if there is an fd leak. open-fd is the only variable that can change with volume restart. How do you re-create the bug?

Pranith

2014-10-13 19:30 GMT+03:00 Roman <romeo.r@xxxxxxxxx>:

Sure.

I'll let it to run for this night .

2014-10-13 19:19 GMT+03:00 Pranith Kumar Karampuri <pkarampu@xxxxxxxxxx>:

hi Roman,
     Do you think we can run this test again? this time, could you enable 'gluster volume profile <volname> start', do the same test. Provide output of 'gluster volume profile <volname> info' and logs after the test?

Pranith

On 10/13/2014 09:45 PM, Roman wrote:

Sure !

root@stor1:~# gluster volume info

Volume Name: HA-2TB-TT-Proxmox-cluster

Type: Replicate

Volume ID: 66e38bde-c5fa-4ce2-be6e-6b2adeaa16c2

Status: Started

Number of Bricks: 1 x 2 = 2

Transport-type: tcp

Bricks:

Brick1: stor1:/exports/HA-2TB-TT-Proxmox-cluster/2TB

Brick2: stor2:/exports/HA-2TB-TT-Proxmox-cluster/2TB

Options Reconfigured:

nfs.disable: 0

network.ping-timeout: 10

Volume Name: HA-WIN-TT-1T

Type: Replicate

Volume ID: 2937ac01-4cba-44a8-8ff8-0161b67f8ee4

Status: Started

Number of Bricks: 1 x 2 = 2

Transport-type: tcp

Bricks:

Brick1: stor1:/exports/NFS-WIN/1T

Brick2: stor2:/exports/NFS-WIN/1T

Options Reconfigured:

nfs.disable: 1

network.ping-timeout: 10

2014-10-13 19:09 GMT+03:00 Pranith Kumar Karampuri <pkarampu@xxxxxxxxxx>:

Could you give your 'gluster volume info' output?

Pranith

On 10/13/2014 09:36 PM, Roman wrote:

Hi,

I've got this kind of setup (servers run replica)

@ 10G backend

gluster storage1

gluster storage2

gluster client1

@1g backend

other gluster clients

Servers got HW RAID5 with SAS disks.

So today I've desided to create a 900GB file for iscsi target that will be located @ glusterfs separate volume, using dd (just a dummy file filled with zeros, bs=1G count 900)

For the first of all the process took pretty lots of time, the writing speed was 130 MB/sec (client port was 2 gbps, servers ports were running @ 1gbps).

Then it reported something like "endpoint is not connected" and all of my VMs on the other volume started to give me IO errors.

Servers load was around 4,6 (total 12 cores)

Maybe it was due to timeout of 2 secs, so I've made it a big higher, 10 sec.

Also during the dd image creation time, VMs very often reported me that their disks are slow like

WARNINGs: Read IO Wait time is -0.02 (outside range [0:1]).

Is 130MB /sec is the maximum bandwidth for all of the volumes in total? That why would we need 10g backends?

HW Raid local speed is 300 MB/sec, so it should not be an issue. any ideas or mby any advices?

Maybe some1 got optimized sysctl.conf for 10G backend?

mine is pretty simple, which can be found from googling.

just to mention: those VM-s were connected using separate 1gbps intraface, which means, they should not be affected by the client with 10g backend.

logs are pretty useless, they just say  this during the outage

[2014-10-13 12:09:18.392910] W [client-handshake.c:276:client_ping_cbk] 0-HA-2TB-TT-Proxmox-cluster-client-0: timer must have expired

[2014-10-13 12:10:08.389708] C [client-handshake.c:127:rpc_client_ping_timer_expired] 0-HA-2TB-TT-Proxmox-cluster-client-0: server 10.250.0.1:49159 has not responded in the last 2 seconds, disconnecting.

[2014-10-13 12:10:08.390312] W [client-handshake.c:276:client_ping_cbk] 0-HA-2TB-TT-Proxmox-cluster-client-0: timer must have expired

so I decided to set the timout a bit higher.

So it seems to me, that under high load GlusterFS is not useable? 130 MB/s is not that much to get some kind of timeouts or makeing the systme so slow, that VM-s feeling themselves bad.

Of course, after the disconnection, healing process was started, but as VM-s lost connection to both of servers, it was pretty useless, they could not run anymore. and BTW, when u load the server with such huge job (dd of 900GB), healing process goes soooooo slow :)

--
Best regards,
Roman.

_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
http://supercolony.gluster.org/mailman/listinfo/gluster-users

--
Best regards,
Roman.

--
Best regards,
Roman.

--
Best regards,
Roman.

_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
http://supercolony.gluster.org/mailman/listinfo/gluster-users